Module: WebSite::RobotsTxt

Included in:
WebSite
Defined in:
lib/wpscan/web_site/robots_txt.rb

Instance Method Summary collapse

Instance Method Details

#has_robots?Boolean

Checks if a robots.txt file exists

Returns:

  • (Boolean)

8
9
10
# File 'lib/wpscan/web_site/robots_txt.rb', line 8

def has_robots?
  Browser.get(robots_url).code == 200
end

#parse_robots_txtArray

Parse robots.txt

Returns:

  • (Array)

    URLs generated from robots.txt


21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
# File 'lib/wpscan/web_site/robots_txt.rb', line 21

def parse_robots_txt
  return unless has_robots?

  return_object = []
  response = Browser.get(robots_url.to_s)
  body = response.body
  # Get all allow and disallow urls
  entries = body.scan(/^(?:dis)?allow:\s*(.*)$/i)
  if entries
    entries.flatten!
    entries.compact.sort!
    wordpress_path = @uri.path
    RobotsTxt.known_dirs.each do |d|
      entries.delete(d)
      # also delete when wordpress is installed in subdir
      dir_with_subdir = "#{wordpress_path}/#{d}".gsub(/\/+/, '/')
      entries.delete(dir_with_subdir)
    end

    entries.each do |d|
      begin
        temp = @uri.clone
        temp.path = d
      rescue URI::Error
        temp = d
      end
      return_object << temp.to_s
    end
  end
  return_object
end

#robots_urlString

Gets a robots.txt URL

Returns:

  • (String)

14
15
16
# File 'lib/wpscan/web_site/robots_txt.rb', line 14

def robots_url
  @uri.clone.merge('robots.txt').to_s
end